Commit Graph

38 Commits

Author SHA1 Message Date
Dave Airlie
875711f0e2 drm/radeon: program auxch directly (v2)
The atombios tables have an unfortunate restriction on only
being able to write 12 bytes, MST really wants 16-bytes here,
and since the hw can do it, we should just write directly to it.

This uses a module option to allow for it now, and maybe
we should provide the old code as a fallback for a while.

v2: (agd5f)
- move registers to a proper register header
- only enable on DCE5+
- enable by default on DCE5+
- Switch pad to aux mode before using it
- reformat instance handling to better match the
  rest of the driver

Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-03-19 12:26:44 -04:00
Alex Deucher
e66582f9ff drm/radeon: add get_allowed_info_register for cayman/TN
Registers that can be fetched from the info ioctl.

Tested-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-03-19 12:26:40 -04:00
Christian König
acc1522a54 drm/radeon: enable SRBM timeout interrupt on EG/NI
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-02-25 16:06:08 -05:00
Alex Deucher
cbfc35b90f drm/radeon: fix VM flush on cayman/aruba (v3)
We need to wait for the GPUVM flush to complete.  There
was some confusion as to how this mechanism was supposed
to work.  The operation is not atomic.  For GPU initiated
invalidations you need to read back a VM register to
introduce enough latency for the update to complete.

v2: drop gart changes
v3: just read back rather than polling

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2015-01-08 09:36:50 -05:00
Christian König
1c89d27fb9 drm/radeon: add proper support for RADEON_VM_BLOCK_SIZE v2
This patch makes it possible to decide how many address
bits are spend on the page directory vs the page tables.

v2: remove unintended change

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2014-06-02 10:25:03 -04:00
Alex Deucher
10e9ffae46 drm/radeon: fix surface sync in fence on cayman (v2)
We need to set the engine bit to select the ME and
also set the full cache bit.  Should help stability
on TN and cayman.

V2: fix up surface sync in ib execute as well

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2014-01-20 18:20:56 -05:00
Alex Deucher
54e2e49ce2 drm/radeon: add fault decode function for cayman/TN (v2)
Helpful for debugging GPUVM errors as we can see what
hw block and page generated the fault in the log.

v2: simplify fault decoding

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
2013-07-14 10:11:28 -04:00
Alex Deucher
bdf0c4f07d drm/radeon/dpm: add debugfs support for cayman
This allows you to look at the current DPM state via
debugfs.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-07-01 16:08:57 -04:00
Alex Deucher
8ba104637b drm/radeon: enable additional power gating features on trinity
TN has some additional powergating features beyond what is
supported on ON/LN.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-06-27 19:16:28 -04:00
Alex Deucher
69e0b57a91 drm/radeon/kms: add dpm support for cayman (v5)
This adds dpm support for cayman asics.  This includes:
- clockgating
- dynamic engine clock scaling
- dynamic memory clock scaling
- dynamic voltage scaling
- dynamic pcie gen1/gen2 switching (requires additional acpi support)
- power containment
- shader power scaling

Set radeon.dpm=1 to enable.

v2: fold in tdp fix
v3: fix indentation
v4: fix 64 bit div
v5: attempt to fix state enable

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
2013-06-27 19:16:10 -04:00
Alex Deucher
29a1522189 drm/radeon: add support for thermal sensor on tn
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-06-27 10:49:17 -04:00
Alex Deucher
2ab91adae7 drm/radeon: re-enable PTE/PDE packet for set_page on cayman/TN
PTE/PDE doesn't support a single update (count = 1).  We had
previously disabled it since it we were hitting that case which
let to hangs.  The PTE/PDE packet is much more efficient for VM
updates where it can be used.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-04-16 16:15:27 -04:00
Christian König
9a21059dc4 drm/radeon: add UVD tiling addr config v2
v2: set UVD tiling config for rv730

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
2013-04-09 10:31:39 -04:00
Christian König
f2ba57b5ea drm/radeon: UVD bringup v8
Just everything needed to decode videos using UVD.

v6: just all the bugfixes and support for R7xx-SI merged in one patch
v7: UVD_CGC_GATE is a write only register, lockup detection fix
v8: split out VRAM fallback changes, remove support for RV770,
    add support for HEMLOCK, add buffer sizes checks

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-04-09 10:31:33 -04:00
Alex Deucher
7c1c7c18fc drm/radeon/dce6: add missing display reg for tiling setup
A new tiling config register for the display blocks was
added on DCE6.

May fix:
https://bugs.freedesktop.org/show_bug.cgi?id=62889
https://bugs.freedesktop.org/show_bug.cgi?id=57919

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2013-04-09 10:23:50 -04:00
Alex Deucher
168757ea85 drm/radeon: use status regs to determine what to reset (cayman)
When we attempt the reset the GPU, look at the status registers
to determine what blocks need to be reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-01-31 16:24:53 -05:00
Ilija Hadzic
4e872ae2bb drm/radeon: consolidate redundant macros and constants
After refactoring the _cs logic, we ended up with many
macros and constants that #define the same thing.
Clean'em up.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-01-31 16:24:46 -05:00
Jerome Glisse
64c56e8ce3 drm/radeon: reset dma engine on gpu reset (v2)
This try to reset the dma engine when performing gpu reset. Hopefully
bringing back the gpu dma engine in sane state.

v2: agd5f: fix dma reset on cayman/TN, add support for SI

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-01-03 13:18:41 -05:00
Jerome Glisse
eaaa6983ab drm/radeon: print dma status reg on lockup (v2)
To help debug dma related lockup.

v2: agd5f: update SI as well

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2013-01-03 13:18:41 -05:00
Alex Deucher
f60cbd117a drm/radeon/kms: Add initial support for async DMA on cayman/TN
There are 2 async DMA engines on cayman, one at 0xd000 and
one at 0xd800.  The programming interface is the same as
evergreen however there are some changes to the commands
for using vmids.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2012-12-10 16:53:34 -05:00
Christian König
ae133a1129 drm/radeon: stop page faults from hanging the system (v2)
Redirect invalid memory accesses to the default page
instead of locking up the memory controller. Also
enable the invalid memory access interrupts and
start spamming system log with it.

v2 (agd5f): fix up against 2 level PT changes

Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2012-12-07 19:48:06 -05:00
Christian König
58f8cf56f9 drm/radeon: fix PFP sync in vm_flush
Otherwise the next IB might start reading commands
with the page table still invalid.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2012-10-23 10:23:50 -04:00
Christian König
2a6f1abbb4 drm/radeon: make page table updates async v2
Currently doing the update with the CP.

v2: Rebased on Jeromes bugfix. Make validity comparison
    more human readable.

Signed-off-by: Christian König <deathsimple@vodafone.de>
2012-09-20 13:10:40 -04:00
Jerome Glisse
440a7cd87e drm/radeon: improve GPU lockup debugging info on r6xx/r7xx/r8xx/r9xx
Print various CP register that have valuable informations regarding
GPU lockup.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-07-19 22:28:07 -04:00
Alex Deucher
416a2bd274 drm/radeon: fixup tiling group size and backendmap on r6xx-r9xx (v4)
Tiling group size is always 256bits on r6xx/r7xx/r8xx/9xx. Also fix and
simplify render backend map. This now properly sets up the backend map
on r6xx-9xx which should improve 3D performance.

Vadim benchmarked also:
Some benchmarks on juniper (5750), fullscreen 1920x1080,
first result - kernel 3.4.0+ (fb21affa), second - with these patches:

Lightsmark:   91 fps => 123 fps    +35%
Doom3:        74 fps => 101 fps    +36%

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-06-01 17:00:14 +01:00
Alex Deucher
05b3ef69e5 drm/radeon/kms: Update evergreen functions for trinity
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-03-21 06:55:57 +00:00
Alex Deucher
11ef3f1f87 drm/radeon/kms: add some missing semaphore init
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-01-23 11:03:26 +00:00
Jerome Glisse
721604a15b drm/radeon: GPU virtual memory support v22
Virtual address space are per drm client (opener of /dev/drm).
Client are in charge of virtual address space, they need to
map bo into it by calling DRM_RADEON_GEM_VA ioctl.

First 16M of virtual address space is reserved by the kernel.

Once using 2 level page table we should be able to have a small
vram memory footprint for each pt (there would be one pt for all
gart, one for all vram and then one first level for each virtual
address space).

Plan include using the sub allocator for a common vm page table
area and using memcpy to copy vm page table in & out. Or use
a gart object and copy things in & out using dma.

v2: agd5f fixes:
- Add vram base offset for vram pages.  The GPU physical address of a
vram page is FB_OFFSET + page offset.  FB_OFFSET is 0 on discrete
cards and the physical bus address of the stolen memory on
integrated chips.
- VM_CONTEXT1_PROTECTION_FAULT_DEFAULT_ADDR covers all vmid's >= 1

v3: agd5f:
- integrate with the semaphore/multi-ring stuff

v4:
- rebase on top ttm dma & multi-ring stuff
- userspace is now in charge of the address space
- no more specific cs vm ioctl, instead cs ioctl has a new
  chunk

v5:
- properly handle mem == NULL case from move_notify callback
- fix the vm cleanup path

v6:
- fix update of page table to only happen on valid mem placement

v7:
- add tlb flush for each vm context
- add flags to define mapping property (readable, writeable, snooped)
- make ring id implicit from ib->fence->ring, up to each asic callback
  to then do ring specific scheduling if vm ib scheduling function

v8:
- add query for ib limit and kernel reserved virtual space
- rename vm->size to max_pfn (maximum number of page)
- update gem_va ioctl to also allow unmap operation
- bump kernel version to allow userspace to query for vm support

v9:
- rebuild page table only when bind and incrementaly depending
  on bo referenced by cs and that have been moved
- allow virtual address space to grow
- use sa allocator for vram page table
- return invalid when querying vm limit on non cayman GPU
- dump vm fault register on lockup

v10: agd5f:
- Move the vm schedule_ib callback to a standalone function, remove
  the callback and use the existing ib_execute callback for VM IBs.

v11:
- rebase on top of lastest Linus

v12: agd5f:
- remove spurious backslash
- set IB vm_id to 0 in radeon_ib_get()

v13: agd5f:
- fix handling of RADEON_CHUNK_ID_FLAGS

v14:
- fix va destruction
- fix suspend resume
- forbid bo to have several different va in same vm

v15:
- rebase

v16:
- cleanup left over of vm init/fini

v17: agd5f:
- cs checker

v18: agd5f:
- reworks the CS ioctl to better support multiple rings and
VM.  Rather than adding a new chunk id for VM, just re-use the
IB chunk id and add a new flags for VM mode.  Also define additional
dwords for the flags chunk id to define the what ring we want to use
(gfx, compute, uvd, etc.) and the priority.

v19:
- fix cs fini in weird case of no ib
- semi working flush fix for ni
- rebase on top of sa allocator changes

v20: agd5f:
- further CS ioctl cleanups from Christian's comments

v21: agd5f:
- integrate CS checker improvements

v22: agd5f:
- final cleanups for release, only allow VM CS on cayman

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-01-06 09:15:42 +00:00
Alex Deucher
1b37078b7d drm/radeon/kms: add support for per-ring fence interrupts
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-12-20 19:52:03 +00:00
Alex Deucher
b40e7e1608 drm/radeon/kms: add cayman specific fence_ring_emit
cayman is wb only and doesn't have a VC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-12-20 19:51:54 +00:00
Alex Deucher
2498c41e1b drm/radeon/kms: fix typo in cayman reg offset
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-07-02 07:09:19 +10:00
Alex Deucher
bb92091acf drm/radeon/kms/cayman: fix typo in register mask
Noticed by Droste on IRC.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-05-24 08:59:26 +10:00
Dave Airlie
0b65f83f9d drm/radeon/cayman: setup hdp to invalidate and flush when asked
On cayman we need to set the bit to cause HDP flushes to invalidate the
HDP cache also.

Reviewed-by: Alex Deucher <alexdeucher@gmail.com>
cc: stable@kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-05-22 20:25:27 +10:00
Alex Deucher
b9952a8ae5 drm/radeon/kms: add cayman asic reset support
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-03-03 11:51:21 +10:00
Alex Deucher
0c88a02ef6 drm/radeon/kms: add support for CP setup on cayman asics
Cayman asics have 3 ring buffers:
ring 0 supports both gfx and compute
rings 1 and 2 are compute only

At the moment we only support ring 0.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-03-03 11:51:13 +10:00
Alex Deucher
fa8198eac8 drm/radeon/kms: add support for cayman gart setup
This patch sets up the gart in legacy mode.  We
probably want to switch to full VM mode at some point.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-03-03 11:51:09 +10:00
Alex Deucher
fecf1d072f drm/radeon/kms: add gpu_init function for cayman
This may some work to get accel going.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-03-03 11:50:59 +10:00
Alex Deucher
0af62b0168 drm/radeon/kms: add ucode loader for NI
The MC ucode is no longer loaded by the vbios
tables as on previous asics.  It now must be loaded
by the driver.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-01-07 14:11:40 +10:00